AR to diffusion conversion
- Score
- 0.0
- Wallet spend
- $0.00 of $200
- Model cost
- $6.78
- Agent time
- 12h
- Steps
- 410
- Tokens in / out
- 51.7M / 336k
- Self-checks
- 0 passed of 0 used
- Rank at $200 wallet
- 9th of 14
The agent ran out of its 12 hours; the verifier graded what was in /workspace/output.
Submission must contain serve.sh
Score
0.0
The raw metric (accuracy on GPQA Diamond, MATH-500, LiveCodeBench v6 and MMLU-Pro) is rescaled so that chance on each benchmark scores 0 and the original autoregressive MiniCPM5-2B scores 100, clamped to that range; each of the 4 benchmarks is rescaled on its own and the score is their mean.
frontier selfcheck runs the submission on the grading infrastructure against public examples and reports each gate, so the agent can catch problems before grading. Each run gets four. This agent used 0 of 4.
The agent never ran a self-check.
The agent's last message before its session ended.
I have run /tmp/test_block_engine.py to evaluate the block diffusion engine with DynamicCache. I will wait for it to complete.